jina-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

jina - Web Content Reader & Search

jina - 网页内容读取与搜索

CLI tool for reading web content and performing AI-powered web searches.

一款用于读取网页内容并执行AI驱动网页搜索的CLI工具。

Quick start

快速开始

Install:

bash

curl -fsSL https://raw.githubusercontent.com/geekjourneyx/jina-cli/main/scripts/install.sh | bash

Basic usage:

bash

undefined

安装:

bash

curl -fsSL https://raw.githubusercontent.com/geekjourneyx/jina-cli/main/scripts/install.sh | bash

基础用法:

bash

undefined

Read a URL

读取URL内容

jina read --url "https://example.com"

Search the web

网页搜索

jina search --query "golang latest news"

undefined

jina search --query "golang latest news"

undefined

Commands

命令列表

Command	Purpose
`read`	Extract and convert content from URLs to LLM-friendly format
`search`	Search the web with AI-powered result processing
`config`	Manage settings (set/get/list/path)

命令	用途
`read`	从URL提取内容并转换为LLM友好的格式
`search`	通过AI驱动的结果处理进行网页搜索
`config`	管理设置（设置/获取/列出/路径）

Read command

Read命令

Extract content from any URL:

bash

undefined

从任意URL提取内容:

bash

undefined

Basic read

基础读取

jina read --url "https://example.com"

Read with image captioning

读取并生成图片说明

jina read -u "https://x.com/user/status/123" --with-alt

Batch process from file

从文件批量处理

jina read --file urls.txt

Output as Markdown

输出为Markdown格式

jina read -u "https://example.com" --output markdown

Save to file

保存到文件

jina read -u "https://example.com" --output-file result.md

undefined

jina read -u "https://example.com" --output-file result.md

undefined

Response formats

返回格式

The API can return content in different formats via

--format

```
markdown
```
- Default, LLM-friendly Markdown
```
html
```
- Raw HTML
```
text
```
- Plain text
```
screenshot
```
- URL to a screenshot

通过

--format

参数，API可返回不同格式的内容:

```
markdown
```
- 默认格式，LLM友好的Markdown
```
html
```
- 原始HTML
```
text
```
- 纯文本
```
screenshot
```
- 截图的URL

Advanced options

高级选项

bash

undefined

bash

undefined

Bypass cache

绕过缓存

jina read -u "https://example.com" --no-cache

Use proxy

使用代理

jina read -u "https://example.com" --proxy "http://proxy.com:8080"

CSS selector extraction

CSS选择器提取

jina read -u "https://example.com" --target-selector "article.main"

Wait for element to load

等待元素加载

jina read -u "https://example.com" --wait-for-selector "#content"

Forward cookies

传递Cookie

jina read -u "https://example.com" --cookie "session=abc123"

POST method for SPA with hash routing

对带哈希路由的SPA使用POST方法

jina read -u "https://example.com/#/route" --post

undefined

jina read -u "https://example.com/#/route" --post

undefined

Search command

Search命令

Search the web with automatic content fetching from top results:

bash

undefined

自动获取顶部搜索结果的内容进行网页搜索:

bash

undefined

Basic search

基础搜索

jina search --query "golang latest news"

Restrict to specific sites

限制到特定站点

jina search -q "AI developments" --site techcrunch.com --site theverge.com

Limit results

限制结果数量

jina search -q "climate change" --limit 10

Output format

输出格式

jina search -q "news" --output markdown

undefined

jina search -q "news" --output markdown

undefined

Site filtering

站点过滤

Use multiple

--site

flags to restrict search to specific domains:

bash

jina search -q "startup funding" --site techcrunch.com --site theverge.com --site wired.com

使用多个

--site

标志将搜索限制到特定域名:

bash

jina search -q "startup funding" --site techcrunch.com --site theverge.com --site wired.com

Configuration

配置

Config file:

~/.jina-reader/config.yaml

Priority: Command args > Environment vars > Config file > Defaults

Environment variables:

```
JINA_API_BASE_URL
```
- Read API URL (default:
```
https://r.jina.ai/
```
)
```
JINA_SEARCH_API_URL
```
- Search API URL (default:
```
https://s.jina.ai/
```
)
```
JINA_TIMEOUT
```
- Request timeout in seconds (default:
```
30
```
)
```
JINA_WITH_GENERATED_ALT
```
- Enable image captioning (default:
```
false
```
)
```
JINA_OUTPUT_FORMAT
```
- Output format: json/markdown (default:
```
json
```
)
```
JINA_PROXY_URL
```
- Proxy server URL

Config commands:

bash

undefined

配置文件:

~/.jina-reader/config.yaml

优先级: 命令行参数 > 环境变量 > 配置文件 > 默认值

环境变量:

```
JINA_API_BASE_URL
```
- 读取API地址（默认:
```
https://r.jina.ai/
```
）
```
JINA_SEARCH_API_URL
```
- 搜索API地址（默认:
```
https://s.jina.ai/
```
）
```
JINA_TIMEOUT
```
- 请求超时时间（秒，默认:
```
30
```
）
```
JINA_WITH_GENERATED_ALT
```
- 启用图片说明生成（默认:
```
false
```
）
```
JINA_OUTPUT_FORMAT
```
- 输出格式: json/markdown（默认:
```
json
```
）
```
JINA_PROXY_URL
```
- 代理服务器地址

配置命令:

bash

undefined

Set configuration

设置配置项

jina config set timeout 60 jina config set with-generated-alt true

View configuration

查看配置

jina config list jina config get timeout jina config path

undefined

jina config list jina config get timeout jina config path

undefined

Output formats

输出格式

JSON format (default, machine-readable):

json

{
  "success": true,
  "data": {
    "url": "https://example.com",
    "content": "# Extracted Content\n\n...",
    "title": "Page Title"
  }
}

Markdown format (human-readable):

bash

jina read -u "https://example.com" --output markdown

JSON格式（默认，机器可读）:

json

{
  "success": true,
  "data": {
    "url": "https://example.com",
    "content": "# Extracted Content\n\n...",
    "title": "Page Title"
  }
}

Markdown格式（人类可读）:

bash

jina read -u "https://example.com" --output markdown

Common use cases

常见用例

Reading social media posts

读取社交媒体帖子

bash

undefined

bash

undefined

X (Twitter) posts

X（Twitter）帖子

jina read -u "https://x.com/elonmusk/status/123456" --with-alt

The --with-alt flag enables VLM image captioning for embedded images

--with-alt标志可为嵌入图片启用VLM图片说明生成

undefined

undefined

Reading articles/blogs

读取文章/博客

bash

undefined

bash

undefined

Standard article

标准文章

jina read -u "https://blog.example.com/article"

With specific format

指定格式

jina read -u "https://example.com" --format text --output markdown

undefined

jina read -u "https://example.com" --format text --output markdown

undefined

Research workflows

研究工作流

bash

undefined

bash

undefined

1. Search for topic

1. 搜索主题

jina search -q "quantum computing 2025" --limit 10

2. Read specific results

2. 读取特定结果

jina read --file search_results.txt

undefined

jina read --file search_results.txt

undefined

Batch processing

批量处理

Create a file with one URL per line:

bash

cat > urls.txt << EOF
https://example.com/page1
https://example.com/page2
https://x.com/user/status/123
EOF

jina read --file urls.txt --output markdown

创建每行一个URL的文件:

bash

cat > urls.txt << EOF
https://example.com/page1
https://example.com/page2
https://x.com/user/status/123
EOF

jina read --file urls.txt --output markdown

Project structure

项目结构

cli/
├── main.go              # Root command
├── read.go              # read command
├── search.go            # search command
├── config.go            # config command
└── pkg/
    ├── api/client.go    # Jina API HTTP client
    ├── config/          # Config file management
    └── output/          # JSON/Markdown formatter

cli/
├── main.go              # 根命令
├── read.go              # read命令
├── search.go            # search命令
├── config.go            # config命令
└── pkg/
    ├── api/client.go    # Jina API HTTP客户端
    ├── config/          # 配置文件管理
    └── output/          # JSON/Markdown格式化工具

Implementation notes

实现说明

Go 1.24+ required
Zero dependencies except Cobra
Single binary distribution
Config stored as simple
```
key=value
```
format (no YAML library dependency)

For API details: See

cli/pkg/api/client.go

需要Go 1.24+
除Cobra外无其他依赖
单二进制分发
配置以简单的
```
key=value
```
格式存储（无YAML库依赖）

API详情: 参见

cli/pkg/api/client.go